Map of % Making Less than 100K in the Bay Area

Based on this map, we can see that a large percentage of people making less than $100K live in the southern regions of the Bay Area. Using CalEnviroScreen data, I plan to analyze how likely those who are from these disadvantaged communities are to face the effects of negative environmental factors such as asthma, and how likely they are to live near waste facilities and struggle with groundwater threats.

First, I am going to test a population indicator (Asthma), against three air quality indicators (Ozone, Pesticide Use, and Toxic Releases from Facilities).

Asthma data retrieval and visualization

Ozone data retrieval and visualization

Pesticides data retrieval and visualization 
`Tox. Release` data retrieval and visualization 
Scatterplots

The scatter plots above show a strong relationship between asthma and toxic releases from facilities. Alternatively, the relationship between asthma and ozone and pesticides seems weak, with the points scattered from from the center line.

Linear Regression Analysis

## 
## Call:
## lm(formula = log(Asthma) ~ Ozone, data = bayarea_asthma__tract)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.12970 -0.46059 -0.02519  0.41458  1.79404 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)   3.9426     0.1378  28.611   <2e-16 ***
## Ozone        -6.3627     3.8038  -1.673   0.0946 .  
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.6916 on 1578 degrees of freedom
## Multiple R-squared:  0.00177,    Adjusted R-squared:  0.001137 
## F-statistic: 2.798 on 1 and 1578 DF,  p-value: 0.09458

## 
## Call:
## lm(formula = log(Asthma) ~ Pesticides, data = bayarea_asthma__tract)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.11706 -0.46207 -0.02622  0.45160  1.78191 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept) 3.712e+00  1.750e-02  212.17   <2e-16 ***
## Pesticides  9.876e-05  1.085e-04    0.91    0.363    
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.6921 on 1578 degrees of freedom
## Multiple R-squared:  0.000525,   Adjusted R-squared:  -0.0001084 
## F-statistic: 0.8289 on 1 and 1578 DF,  p-value: 0.3627

## 
## Call:
## lm(formula = log(Asthma) ~ `Tox. Release`, data = bayarea_asthma__tract)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -3.02998 -0.43918  0.00386  0.45439  1.70049 
## 
## Coefficients:
##                 Estimate Std. Error t value Pr(>|t|)    
## (Intercept)    3.623e+00  2.057e-02 176.150  < 2e-16 ***
## `Tox. Release` 2.135e-04  2.683e-05   7.958 3.31e-15 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.6788 on 1578 degrees of freedom
## Multiple R-squared:  0.03859,    Adjusted R-squared:  0.03798 
## F-statistic: 63.33 on 1 and 1578 DF,  p-value: 3.306e-15

On the linear regression analysis, Asthma vs. Toxic Releases, again shows a positive relationship. The relationship between asthma and pesticides; however, seems to be slightly more positive than it was before. The ozone data does not demonstrate a correlation.

Next, I decided to test a socioeconomic factor (poverty) against three environmental effects indicators (Groundwater threats, Hazardous Waste, and Solid waste sites/facilities).

Poverty data retrieval and visualization 
`Groundwater Threats` data retrieval and visualization 
`Haz. Waste` data retrieval and visualization 
`Solid Waste` data retrieval and visualization 
Scatterplots

Each scatter plot demonstrates a positive relationship between poverty and each of exposure to hazardous waste, solid waste, and groundwater threats. The strongest relationship is between poverty and groundwater threats.

Linear Regression Analysis

## 
## Call:
## lm(formula = log(Poverty) ~ `Groundwater Threats`, data = bayarea_Poverty__tract)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.72906 -0.46085  0.03287  0.49876  1.70105 
## 
## Coefficients:
##                       Estimate Std. Error t value Pr(>|t|)    
## (Intercept)           2.696162   0.019896 135.512   <2e-16 ***
## `Groundwater Threats` 0.003374   0.000377   8.948   <2e-16 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.6713 on 1571 degrees of freedom
## Multiple R-squared:  0.0485, Adjusted R-squared:  0.04789 
## F-statistic: 80.07 on 1 and 1571 DF,  p-value: < 2.2e-16

## 
## Call:
## lm(formula = log(Poverty) ~ `Haz. Waste`, data = bayarea_Poverty__tract)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.78135 -0.46379  0.02721  0.49529  1.70676 
## 
## Coefficients:
##              Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  2.760480   0.019150 144.154   <2e-16 ***
## `Haz. Waste` 0.033657   0.009486   3.548    4e-04 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.6855 on 1571 degrees of freedom
## Multiple R-squared:  0.007949,   Adjusted R-squared:  0.007317 
## F-statistic: 12.59 on 1 and 1571 DF,  p-value: 0.0003998

## 
## Call:
## lm(formula = log(Poverty) ~ `Solid Waste`, data = bayarea_Poverty__tract)
## 
## Residuals:
##      Min       1Q   Median       3Q      Max 
## -2.77988 -0.45871  0.02217  0.49372  1.62537 
## 
## Coefficients:
##               Estimate Std. Error t value Pr(>|t|)    
## (Intercept)   2.756652   0.018436 149.524  < 2e-16 ***
## `Solid Waste` 0.023232   0.004633   5.014 5.94e-07 ***
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.6828 on 1571 degrees of freedom
## Multiple R-squared:  0.01575,    Adjusted R-squared:  0.01512 
## F-statistic: 25.14 on 1 and 1571 DF,  p-value: 5.937e-07

Based on the linear regression analysis, the relationship between poverty and groundwater remains the strongest followed by the relationship between poverty and solid waste.

From this entire analysis, I can conclude that people from disadvantaged/low-income areas are likely to be exposed to solid waste sites/facilities, hazardous waste, and groundwater threats. Each of these indicators pose a significant threat to the livelihood of communities. Regarding groundwater threats, thousands of storage tanks in CA have leaked petroleum or other haz. substances that degrade the quality of local soil and groundwater. For solid waste and hazardous waste, areas that are in poverty are likely to contain older landfills that may expose nearby residents to contaminated air, water, and soil. From my analysis of asthma, we can conclude that toxic releases from facilities, which are likely to be found in areas struggling with poverty, is likely to be one of the causes of asthma. Although there was not a strong correlation between asthma and ozone and pesticide use, it is possible that they can have a positive relationship with cardiovascular disease instead.